ai-intervention-agent
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ai-intervention-agentask user to review current context and provide feedback on the plan"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
When using AI CLIs/IDEs, agents can drift from your intent. This project gives you a simple way to intervene at key moments, review context in a Web UI, and send your latest instructions via interactive_feedback so the agent can continue on track.
Works with Cursor, VS Code, Claude Code, Augment, Windsurf, Trae, and more.
Quick start
Install:
pip install ai-intervention-agent
# or
uv add ai-intervention-agentConfigure your AI tool to launch the MCP server via
uvx:
{
"mcpServers": {
"ai-intervention-agent": {
"command": "uvx",
"args": ["ai-intervention-agent"],
"timeout": 600,
"autoApprove": ["interactive_feedback"]
}
}
}>interactive_feedback is a long-running tool. Some clients have a hard request timeout, so the Web UI provides a countdown + auto re-submit option to keep sessions alive.
- Only ask me through the MCP `ai-intervention-agent` tool; do not ask directly in chat or ask for end-of-task confirmation in chat.
- If a tool call fails, keep asking again through `ai-intervention-agent` instead of making assumptions, until the tool call succeeds.
ai-intervention-agent usage details:
- If requirements are unclear, use `ai-intervention-agent` to ask for clarification with predefined options.
- If there are multiple approaches, use `ai-intervention-agent` to ask instead of deciding unilaterally.
- If a plan/strategy needs to change, use `ai-intervention-agent` to ask instead of deciding unilaterally.
- Before finishing a request, always ask for feedback via `ai-intervention-agent`.
- Do not end the conversation/request unless the user explicitly allows it via `ai-intervention-agent`.Related MCP server: AI Intervention Agent
Screenshots
Key features
Real-time intervention: the agent pauses and waits for your input via
interactive_feedbackWeb UI: Markdown, code highlighting, and math rendering
Multi-task: tab switching with independent countdown timers
Auto re-submit: keep sessions alive by auto-submitting at timeout
Notifications: web / sound / system / Bark
SSH-friendly: great with port forwarding
VS Code extension (optional)
Item | Value |
Purpose | Embed the interaction panel into VS Code’s sidebar to avoid switching to a browser. |
Install (Open VSX) | |
Download VSIX (GitHub Release) | |
Setting |
|
Configuration
Item | Value |
Docs (English) | |
Docs (简体中文) | |
Default template |
|
OS | User config directory |
Linux |
|
macOS |
|
Windows |
|
Architecture
flowchart TD
subgraph CLIENTS["AI clients"]
AI_CLIENT["AI CLI / IDE<br/>(Cursor, VS Code, Claude Code, ...)"]
end
subgraph MCP_PROC["MCP server process"]
MCP_SRV["ai-intervention-agent<br/>(server.py)"]
MCP_TOOL["MCP tool<br/>interactive_feedback"]
CFG_MGR["Config manager<br/>(config_manager.py)"]
NOTIF_MGR["Notification manager<br/>(notification_manager.py)"]
end
subgraph WEB_PROC["Web UI process"]
WEB_SRV["Web UI service<br/>(web_ui.py / Flask)"]
HTTP_API["HTTP API<br/>(/api/*)"]
TASK_Q["Task queue<br/>(task_queue.py)"]
WEB_SRV --> HTTP_API
WEB_SRV --> TASK_Q
end
subgraph USER_UI["User interfaces"]
BROWSER["Browser"]
VSCODE["VS Code extension<br/>(Webview)"]
end
CFG_FILE["config.jsonc<br/>(user config directory)"]
AI_CLIENT -->|MCP call| MCP_TOOL
MCP_SRV -->|exposes| MCP_TOOL
MCP_TOOL -->|ensure Web UI running| WEB_SRV
MCP_TOOL <-->|create task / poll result| HTTP_API
BROWSER <-->|HTTP| HTTP_API
VSCODE <-->|HTTP| HTTP_API
CFG_MGR <-->|read/write| CFG_FILE
WEB_SRV <-->|read| CFG_FILE
MCP_SRV --> NOTIF_MGR
NOTIF_MGR -->|web / sound / system / Bark| USER["User"]Documentation
API docs index:
docs/api/index.mdAPI docs (简体中文):
docs/api.zh-CN/index.md
Related projects
License
MIT License
This server cannot be deployed
Maintenance
Related MCP Connectors
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
Agent-ready feedback for AI-built apps — read and close UI feedback reports over MCP.
EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to request human input through a web interface, allowing them to pause execution and wait for responses via interactive tools like single questions, multiple choice selections, hypothesis challenges, and decision workflows.5 npm2MIT
- AlicenseAqualityAmaintenanceEnables real-time user intervention for MCP agents through a web UI, allowing users to review context and provide feedback when AI agents drift from intent, keeping them on track.116MIT
- AlicenseNot gradedqualityCmaintenanceEnables human-in-the-loop checkpoints for AI agents, allowing them to pause and wait for human input via a web UI, then seamlessly resume execution.28MIT
- FlicenseNot gradedqualityDmaintenanceEnables agents to request and receive user feedback during task execution through a terminal-based interactive feedback system.10-